Skip to content
Conference

MonoPRIO: CLIP-Conditioned Size Priors for Monocular 3D Detection

Aug 2026 · 2026 IEEE 22nd International Conference on Automation Science and Engineering (CASE) · pp. 2816-2821 · 0 citations · 20 references

Abstract

Monocular 3D object detection is attractive for autonomous systems because it offers low-cost, easy-to-integrate perception, but recovering metric geometry from a single image remains ill-posed, especially under occlusion, truncation, and class imbalance. Recent methods improve depth and context reasoning, yet size and depth estimates remain coupled and unstable in ambiguous unified multi-class settings. We propose MonoPRIO, a prior-conditioned extension of MonoDGP that uses offline class-aware size prior banks and query-level adaptive prior routing to stabilise size estimation. MonoPRIO combines routed mixture priors with uncertainty-aware logspace size conditioning and Cluster Aligned Prior (CAP) regularisation on matched positives to keep predictions near plausible prototype manifolds. Prior construction is offline, enabling lightweight online inference without additional prior-feature extraction. On KITTI, MonoPRIO achieves the strongest fully reported unified multi-class result on the official KITTI benchmark test split and the best unified validation medians among compared methods. It improves unified accuracy over MonoDGP while preserving a near-identical compute budget, and a compact mechanism ablation shows that routed prior injection and CAP jointly improve the accuracy-size-fidelity trade-off.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.